Model: GELU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1842 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-3l')

Text #0

Max Range: 3.3797. Min Range: -3.3797

Max Act: 3.3797. Min Act: -0.1700

Data Index: 1515424 (Python Code)

Max Activating Token Index: 273

Text #1

Max Range: 3.3797. Min Range: -3.3797

Max Act: 3.2384. Min Act: -0.1700

Data Index: 1560777 (Python Code)

Max Activating Token Index: 15

Text #2

Max Range: 3.3797. Min Range: -3.3797

Max Act: 3.1755. Min Act: -0.1700

Data Index: 1648443 (Python Code)

Max Activating Token Index: 779

Text #3

Max Range: 3.3797. Min Range: -3.3797

Max Act: 3.1912. Min Act: -0.1700

Data Index: 1477738 (Python Code)

Max Activating Token Index: 278

Text #4

Max Range: 3.3797. Min Range: -3.3797

Max Act: 3.1912. Min Act: -0.1700

Data Index: 1411325 (Python Code)

Max Activating Token Index: 154

Text #5

Max Range: 3.3797. Min Range: -3.3797

Max Act: 3.1755. Min Act: -0.1700

Data Index: 1649635 (Python Code)

Max Activating Token Index: 141

Text #6

Max Range: 3.3797. Min Range: -3.3797

Max Act: 3.1755. Min Act: -0.1700

Data Index: 1394602 (Python Code)

Max Activating Token Index: 520

Text #7

Max Range: 3.3797. Min Range: -3.3797

Max Act: 3.1440. Min Act: -0.1700

Data Index: 1587636 (Python Code)

Max Activating Token Index: 396

Text #8

Max Range: 3.3797. Min Range: -3.3797

Max Act: 3.1597. Min Act: -0.1700

Data Index: 1560542 (Python Code)

Max Activating Token Index: 60

Text #9

Max Range: 3.3797. Min Range: -3.3797

Max Act: 3.1597. Min Act: -0.1700

Data Index: 1395897 (Python Code)

Max Activating Token Index: 66

Text #10

Max Range: 3.3797. Min Range: -3.3797

Max Act: 3.1597. Min Act: -0.1700

Data Index: 1527065 (Python Code)

Max Activating Token Index: 58

Text #11

Max Range: 3.3797. Min Range: -3.3797

Max Act: 3.1597. Min Act: -0.1700

Data Index: 1380223 (Python Code)

Max Activating Token Index: 8

Text #12

Max Range: 3.3797. Min Range: -3.3797

Max Act: 3.1597. Min Act: -0.1700

Data Index: 1576456 (Python Code)

Max Activating Token Index: 486

Text #13

Max Range: 3.3797. Min Range: -3.3797

Max Act: 3.1282. Min Act: -0.1700

Data Index: 1519258 (Python Code)

Max Activating Token Index: 356

Text #14

Max Range: 3.3797. Min Range: -3.3797

Max Act: 3.1282. Min Act: -0.1700

Data Index: 1583419 (Python Code)

Max Activating Token Index: 41

Text #15

Max Range: 3.3797. Min Range: -3.3797

Max Act: 3.1440. Min Act: -0.1700

Data Index: 1525242 (Python Code)

Max Activating Token Index: 52

Text #16

Max Range: 3.3797. Min Range: -3.3797

Max Act: 3.1282. Min Act: -0.1700

Data Index: 1499358 (Python Code)

Max Activating Token Index: 21

Text #17

Max Range: 3.3797. Min Range: -3.3797

Max Act: 3.1440. Min Act: -0.1700

Data Index: 1506231 (Python Code)

Max Activating Token Index: 177

Text #18

Max Range: 3.3797. Min Range: -3.3797

Max Act: 3.1282. Min Act: -0.1700

Data Index: 1583312 (Python Code)

Max Activating Token Index: 455

Text #19

Max Range: 3.3797. Min Range: -3.3797

Max Act: 3.1282. Min Act: -0.1700

Data Index: 1556863 (Python Code)

Max Activating Token Index: 126